Google Is Adding an'AI Inbox' to Gmail That Summarizes Emails New Gmail features, powered by the Gemini model, are part of Google's continued push for users to incorporate AI into their daily life and conversations. Google is putting even more generative AI tools into Gmail as part of its goal to further personalize user inboxes and streamline searches. On Thursday, the company announced a new "AI Inbox" tab, currently in a beta testing phase, that reads every message in a user's Gmail and suggests a list of to-dos and key topics, based on what it summarizes . In Google's example of what this AI Inbox could look like in Gmail, the new tab takes context from a user's messages and suggests they reschedule their dentist appointment, reply to a request from their child's sports coach, and pay an upcoming fee before the deadline. Also under the AI Inbox tab is a list of important topics worth browsing, nestled beneath the action items at the top.

Workers were randomly selected to access a generative AI tool integrated into applications they already used at work for email, meetings, and writing. In the second half of the 6-month experiment, the 80% of treated workers who used this tool spent two fewer hours on email each week and reduced their time working outside of regular hours. Apart from these individual time savings, we do not detect shifts in the quantity or composition of workers' tasks resulting from individual-level AI provision. Generative AI has opened new possibilities for technology to assist with or automate a variety of tasks. Early studies have already shown that generative AI increases worker productivity in targeted tasks (e.g.

Large language models (LLMs) have become increasingly popular due to their ability to interact with unstructured content. As such, LLMs are now a key driver behind the automation of language processing systems, such as AI agents. Unfortunately, these advantages have come with a vulnerability to prompt injections, an attack where an adversary subverts the LLM's intended functionality with an injected task. Past approaches have proposed detectors and finetuning to provide robustness, but these techniques are vulnerable to adaptive attacks or cannot be used with state-of-the-art models. To this end we propose type-directed privilege separation for LLMs, a method that systematically prevents prompt injections. We restrict the ability of an LLM to interact with third-party data by converting untrusted content to a curated set of data types; unlike raw strings, each data type is limited in scope and content, eliminating the possibility for prompt injections. We evaluate our method across several case studies and find that designs leveraging our principles can systematically prevent prompt injection attacks while maintaining high utility.

Artificial intelligence--and in particular generative AI--continues to push its way into every aspect of digital life, with varying degrees of success. One of the latest updates from Google adds the Gemini AI chatbot to Gmail on Android and iOS, which means you can ask questions about anything in your inbox. For example, you might want a summary of a discussion you've been having with your boss or need a reminder about when an upcoming camping trip is actually happening. For queries like these, Gemini can dive into your email threads and pull out the salient details for you. This is separate to the Gemini text creation tools you get when composing emails in Gmail on the web, and--for the time being at least--it's exclusive to those with a paid Google Workspace account or a subscription to the Google One AI Premium plan.

Google is making Gemini more easily accessible in its Workspace apps, if you're a paying customer. The company is rolling out Gemini side panels for Docs, Sheets, Slides, Drive and Gmail, and it has also launched Gemini for the Gmail app on Android and iOS. When Google announced the Gemini side panels at I/O this year, it called the feature "the connective tissue across multiple applications with AI-powered workflow." The side panel in Docs will help you refine and rephrase what you're writing, summarize information, suggest improvements and create new content based on other files. In Sheets, it can help you create tables, generate formulas and demystify various Sheets functions by teaching you how to do certain tasks.

Google is adding Gemini-powered AI automation to more tasks in Workspace. In its Tuesday Google I/O keynote, the company said its advanced Gemini 1.5 Pro will soon be available in the Workspace side panel as "the connective tissue across multiple applications with AI-powered workflows," as AI grows more intelligent, learns more about you and automates more of your workflow. Gemini's job in Workspace is to save you the time and effort of digging through files, emails and other data from multiple apps. "Workspace in the Gemini era will continue to unlock new ways of getting things done," Google Workspace VP Aparna Pappu said at the event. The refreshed Workspace side panel, coming first to Gmail, Docs, Sheets, Slides and Drive, will let you chat with Gemini about your content.

Cyber deception is emerging as a promising approach to defending networks and systems against attackers and data thieves. However, despite being relatively cheap to deploy, the generation of realistic content at scale is very costly, due to the fact that rich, interactive deceptive technologies are largely hand-crafted. With recent improvements in Machine Learning, we now have the opportunity to bring scale and automation to the creation of realistic and enticing simulated content. In this work, we propose a framework to automate the generation of email and instant messaging-style group communications at scale. Such messaging platforms within organisations contain a lot of valuable information inside private communications and document attachments, making them an enticing target for an adversary. We address two key aspects of simulating this type of system: modelling when and with whom participants communicate, and generating topical, multi-party text to populate simulated conversation threads. We present the LogNormMix-Net Temporal Point Process as an approach to the first of these, building upon the intensity-free modeling approach of Shchur et al. to create a generative model for unicast and multi-cast communications. We demonstrate the use of fine-tuned, pre-trained language models to generate convincing multi-party conversation threads. A live email server is simulated by uniting our LogNormMix-Net TPP (to generate the communication timestamp, sender and recipients) with the language model, which generates the contents of the multi-party email threads. We evaluate the generated content with respect to a number of realism-based properties, that encourage a model to learn to generate content that will engage the attention of an adversary to achieve a deception outcome.

Recent years have brought about an interest in the challenging task of summarizing conversation threads (meetings, online discussions, etc.). Such summaries help analysis of the long text to quickly catch up with the decisions made and thus improve our work or communication efficiency. To spur research in thread summarization, we have developed an abstractive Email Thread Summarization (EmailSum) dataset, which contains human-annotated short (<30 words) and long (<100 words) summaries of 2549 email threads (each containing 3 to 10 emails) over a wide variety of topics. We perform a comprehensive empirical study to explore different summarization techniques (including extractive and abstractive methods, single-document and hierarchical models, as well as transfer and semisupervised learning) and conduct human evaluations on both short and long summary generation tasks. Our results reveal the key challenges of current abstractive summarization models in this task, such as understanding the sender's intent and identifying the roles of sender and receiver. Furthermore, we find that widely used automatic evaluation metrics (ROUGE, BERTScore) are weakly correlated with human judgments on this email thread summarization task. Hence, we emphasize the importance of human evaluation and the development of better metrics by the community. Our code and summary data have been made available at: https://github.com/ZhangShiyue/EmailSum

We present the first large scale corpus for entity resolution in email conversations (CEREC). The corpus consists of 6001 email threads from the Enron Email Corpus containing 36,448 email messages and 60,383 entity coreference chains. The annotation is carried out as a two-step process with minimal manual effort. Experiments are carried out for evaluating different features and performance of four baselines on the created corpus. For the task of mention identification and coreference resolution, a best performance of 59.2 F1 is reported, highlighting the room for improvement. An in-depth qualitative and quantitative error analysis is presented to understand the limitations of the baselines considered.

Sophisticated threat actors can often maintain a long-term presence in their target environments for months at a time, without being detected. They move slowly and with caution, to evade traditional security controls and are often targeted to specific individuals and organizations. AI will also be able to learn the dominant communication channels and the best ports and protocols to use to move around a system, discretely blending in with routine activity. This ability to disguise itself amid the noise will mean that it is able to expertly spread within a digital environment, and stealthily compromise more devices than ever before. AI malware will also be able to analyse vast volumes of data at machine speed, rapidly identifying which data sets are valuable and which are not. This will save the (human) attacker a great deal of time and effort.